© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20850
    Prev
    Next
    INDEX
    Explanations

    payment amounts or purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pasaj
    -0.08
    ály
    -0.08
    ën
    -0.08
    ì§ĵ
    -0.07
    RAFT
    -0.07
    sey
    -0.07
    arana
    -0.07
    yks
    -0.07
     Unidas
    -0.07
    ouple
    -0.07
    POSITIVE LOGITS
    isbury
    0.08
    ask
    0.07
    ings
    0.07
    ä¸įåĩºåİ»
    0.07
    å¾Ĺèµ·
    0.07
    staking
    0.07
    å°Ķæĸ¯
    0.07
    ackt
    0.07
    itive
    0.07
    incipal
    0.06
    Activations Density 0.036%

    No Known Activations